Borrowing it
Nothing to install: this file belongs to gastonrey/licita-app. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/gastonrey/licita-app/main/AGENTS.mdgit clone --depth 1 https://github.com/gastonrey/licita-appWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/gastonrey/licita-app/agents-md)<a href="https://agentmods.dev/instructions/gastonrey/licita-app/agents-md"><img src="https://agentmods.dev/badge/instructions/gastonrey/licita-app/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/gastonrey/licita-app/agents-md"><img src="https://agentmods.dev/badge/instructions/gastonrey/licita-app/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00988 | $0.00988 |
| Opus 5.5 | $0.00395 | $0.00395 |
| Sonnet 5.5 | $0.00198 | $0.00198 |
| Haiku 4.5 | $0.00099 | $0.00099 |
Grade A, and why
licita-app AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Relicita Project Guidelines
Product context
Relicita is an agent-native public procurement intelligence product for professional teams. It indexes TED and, when enabled, PLACSP data to expose evidence-backed intelligence about tenders, buyers, suppliers, opportunities, and renewal signals through REST and MCP. The package name stays licita-agent and the MCP registry id stays licita.
Primary users:
- Procurement and business-development professionals evaluating public-sector opportunities.
- AI-agent and integration developers consuming the REST/MCP surfaces.
- The operator monitoring acquisition, usage, revenue, and data quality.
The primary product outcome is helping a professional decide where to focus procurement activity next. Human-facing UX must lead with that decision value; protocol, payment, and implementation details are secondary.
Engineering conventions
- Runtime: Node.js 22+, TypeScript, ESM, Fastify, PostgreSQL, raw SQL, and Zod validation. (Floor set by
engines; jsdom/undici 8 in the test stack requires Node ≥ 22.19.) - Public web surfaces live in
src/web/; API routes live insrc/api/routes/; payments live insrc/pay/; migrations live inmigrations/; tests live intest/. - Preserve REST envelopes, MCP contracts, provenance, and explicit nulls. Never fabricate data.
- Validate untrusted input at the route boundary and enforce authorization server-side.
- Migrations are additive and replay-safe. Never modify production secrets or unrelated tooling files.
- Keep the public discovery surfaces stable:
/llms.txt,/openapi.json,/v1/pricing,/docs,/mcp, the MCP server card, use-case/data routes, and/robots.txt.
Commands
npm test
npm run test:integration
npm run test:api-smoke
npm run typecheck
npm run build
Local services:
docker compose up --build -d
docker compose logs -f app
Definition of done
- The user, primary job, decision, scope, and acceptance scenarios are explicit.
- Tests are written before implementation for new behavior (strict TDD).
npm test, relevant integration/smoke tests, typecheck, and build pass.- Error, empty, loading, success, and disabled states are covered.
- Security, privacy, authorization, and data-retention implications are reviewed.
- Public API, MCP, discovery, and provenance contracts have regression coverage.
- Documentation, deployment, and rollback notes are updated when applicable.
- No UI is considered complete without browser evidence or an explicit
Needs verificationdecision.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago Changed · +21 tokens per session 6859faaa9b0d
- 2mo ago Changed · +27 tokens per session cfcfb236c1e7
- 2mo ago First seen · 97 lines · 940 tokens per session scan A 93d8a56176fb
licita-app AGENTS.md is an instructions file published in the GitHub repository gastonrey/licita-app (0 stars, last pushed 5d ago), licensed MIT. It adds 988 tokens to every session, about $0.0040 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.
licita-app AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| licita-app AGENTS.mdgastonrey/licita-app | Instructions file | 0 | 5d ago | MIT | A | 988 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |